"auto-commit"
Browse files- model-bin/finetune/base/{checkpoint-28240 → checkpoint-28862}/config.json +0 -0
- model-bin/finetune/base/{checkpoint-28240 → checkpoint-28862}/optimizer.pt +1 -1
- model-bin/finetune/base/{checkpoint-28240 → checkpoint-28862}/preprocessor_config.json +0 -0
- model-bin/finetune/base/{checkpoint-28240 → checkpoint-28862}/pytorch_model.bin +1 -1
- model-bin/finetune/base/{checkpoint-28240 → checkpoint-28862}/rng_state.pth +1 -1
- model-bin/finetune/base/{checkpoint-28240 → checkpoint-28862}/scaler.pt +1 -1
- model-bin/finetune/base/{checkpoint-28240 → checkpoint-28862}/scheduler.pt +1 -1
- model-bin/finetune/base/{checkpoint-28240 → checkpoint-28862}/trainer_state.json +421 -4
- model-bin/finetune/base/{checkpoint-28240 → checkpoint-28862}/training_args.bin +0 -0
- model-bin/finetune/base/log/1629621463.5203574/events.out.tfevents.1629621463.91f414e9573a.903.91 +3 -0
- model-bin/finetune/base/log/1629622131.5072112/events.out.tfevents.1629622131.91f414e9573a.903.93 +3 -0
- model-bin/finetune/base/log/1629622785.7860968/events.out.tfevents.1629622785.91f414e9573a.903.95 +3 -0
- model-bin/finetune/base/log/1629623445.3943064/events.out.tfevents.1629623445.91f414e9573a.903.97 +3 -0
- model-bin/finetune/base/log/1629624114.9649696/events.out.tfevents.1629624114.91f414e9573a.903.99 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629621463.91f414e9573a.903.90 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629622131.91f414e9573a.903.92 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629622785.91f414e9573a.903.94 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629623445.91f414e9573a.903.96 +3 -0
- model-bin/finetune/base/log/events.out.tfevents.1629624114.91f414e9573a.903.98 +3 -0
model-bin/finetune/base/{checkpoint-28240 → checkpoint-28862}/config.json
RENAMED
|
File without changes
|
model-bin/finetune/base/{checkpoint-28240 → checkpoint-28862}/optimizer.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 722165009
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0cddb4b40f8ff2b570af005ac4764735d0d8de1b17574dc0ff23ce028419e3c1
|
| 3 |
size 722165009
|
model-bin/finetune/base/{checkpoint-28240 → checkpoint-28862}/preprocessor_config.json
RENAMED
|
File without changes
|
model-bin/finetune/base/{checkpoint-28240 → checkpoint-28862}/pytorch_model.bin
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 377909911
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e85113060e747ea9bba898df759c69952c9bc7c29f6aae86e5690a17913c648b
|
| 3 |
size 377909911
|
model-bin/finetune/base/{checkpoint-28240 → checkpoint-28862}/rng_state.pth
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71cdeb1b4ccad9e7e3eeac33394c7b95c1939e4c6bb4c46cc6c4e8546b22da5e
|
| 3 |
size 14503
|
model-bin/finetune/base/{checkpoint-28240 → checkpoint-28862}/scaler.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 559
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ebe06984898cda1bbba256d5887e5cdb0d404ad78219ebc56e7326a6a83a5e61
|
| 3 |
size 559
|
model-bin/finetune/base/{checkpoint-28240 → checkpoint-28862}/scheduler.pt
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3eae9f8f6a6d1a55d3a8afb32127eaa6c56f1b7d56ddc2fb2b251338bb9dba0e
|
| 3 |
size 623
|
model-bin/finetune/base/{checkpoint-28240 → checkpoint-28862}/trainer_state.json
RENAMED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.2158154859967051,
|
| 3 |
"best_model_checkpoint": "./model-bin/finetune/base/checkpoint-25631",
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -141273,11 +141273,428 @@
|
|
| 141273 |
"eval_steps_per_second": 0.666,
|
| 141274 |
"eval_wer": 0.2228188906870678,
|
| 141275 |
"step": 28240
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 141276 |
}
|
| 141277 |
],
|
| 141278 |
-
"max_steps":
|
| 141279 |
"num_train_epochs": 5000,
|
| 141280 |
-
"total_flos":
|
| 141281 |
"trial_name": null,
|
| 141282 |
"trial_params": null
|
| 141283 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.2158154859967051,
|
| 3 |
"best_model_checkpoint": "./model-bin/finetune/base/checkpoint-25631",
|
| 4 |
+
"epoch": 230.0,
|
| 5 |
+
"global_step": 28862,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 141273 |
"eval_steps_per_second": 0.666,
|
| 141274 |
"eval_wer": 0.2228188906870678,
|
| 141275 |
"step": 28240
|
| 141276 |
+
},
|
| 141277 |
+
{
|
| 141278 |
+
"epoch": 227.08,
|
| 141279 |
+
"learning_rate": 9.559935379644589e-06,
|
| 141280 |
+
"loss": 0.3802,
|
| 141281 |
+
"step": 28250
|
| 141282 |
+
},
|
| 141283 |
+
{
|
| 141284 |
+
"epoch": 227.16,
|
| 141285 |
+
"learning_rate": 9.559773828756059e-06,
|
| 141286 |
+
"loss": 0.4891,
|
| 141287 |
+
"step": 28260
|
| 141288 |
+
},
|
| 141289 |
+
{
|
| 141290 |
+
"epoch": 227.24,
|
| 141291 |
+
"learning_rate": 9.559612277867529e-06,
|
| 141292 |
+
"loss": 0.8936,
|
| 141293 |
+
"step": 28270
|
| 141294 |
+
},
|
| 141295 |
+
{
|
| 141296 |
+
"epoch": 227.32,
|
| 141297 |
+
"learning_rate": 9.559450726978999e-06,
|
| 141298 |
+
"loss": 0.4074,
|
| 141299 |
+
"step": 28280
|
| 141300 |
+
},
|
| 141301 |
+
{
|
| 141302 |
+
"epoch": 227.4,
|
| 141303 |
+
"learning_rate": 9.559289176090469e-06,
|
| 141304 |
+
"loss": 0.9653,
|
| 141305 |
+
"step": 28290
|
| 141306 |
+
},
|
| 141307 |
+
{
|
| 141308 |
+
"epoch": 227.48,
|
| 141309 |
+
"learning_rate": 9.559127625201939e-06,
|
| 141310 |
+
"loss": 0.44,
|
| 141311 |
+
"step": 28300
|
| 141312 |
+
},
|
| 141313 |
+
{
|
| 141314 |
+
"epoch": 227.56,
|
| 141315 |
+
"learning_rate": 9.558966074313409e-06,
|
| 141316 |
+
"loss": 0.5189,
|
| 141317 |
+
"step": 28310
|
| 141318 |
+
},
|
| 141319 |
+
{
|
| 141320 |
+
"epoch": 227.64,
|
| 141321 |
+
"learning_rate": 9.558804523424879e-06,
|
| 141322 |
+
"loss": 0.9151,
|
| 141323 |
+
"step": 28320
|
| 141324 |
+
},
|
| 141325 |
+
{
|
| 141326 |
+
"epoch": 227.72,
|
| 141327 |
+
"learning_rate": 9.558642972536349e-06,
|
| 141328 |
+
"loss": 0.3856,
|
| 141329 |
+
"step": 28330
|
| 141330 |
+
},
|
| 141331 |
+
{
|
| 141332 |
+
"epoch": 227.8,
|
| 141333 |
+
"learning_rate": 9.558481421647819e-06,
|
| 141334 |
+
"loss": 0.9493,
|
| 141335 |
+
"step": 28340
|
| 141336 |
+
},
|
| 141337 |
+
{
|
| 141338 |
+
"epoch": 227.88,
|
| 141339 |
+
"learning_rate": 9.558319870759289e-06,
|
| 141340 |
+
"loss": 0.4099,
|
| 141341 |
+
"step": 28350
|
| 141342 |
+
},
|
| 141343 |
+
{
|
| 141344 |
+
"epoch": 227.96,
|
| 141345 |
+
"learning_rate": 9.55815831987076e-06,
|
| 141346 |
+
"loss": 0.5333,
|
| 141347 |
+
"step": 28360
|
| 141348 |
+
},
|
| 141349 |
+
{
|
| 141350 |
+
"epoch": 228.0,
|
| 141351 |
+
"eval_loss": 0.5005343556404114,
|
| 141352 |
+
"eval_runtime": 40.761,
|
| 141353 |
+
"eval_samples_per_second": 20.632,
|
| 141354 |
+
"eval_steps_per_second": 0.662,
|
| 141355 |
+
"eval_wer": 0.22580168464607656,
|
| 141356 |
+
"step": 28364
|
| 141357 |
+
},
|
| 141358 |
+
{
|
| 141359 |
+
"epoch": 228.05,
|
| 141360 |
+
"learning_rate": 9.55799676898223e-06,
|
| 141361 |
+
"loss": 0.4313,
|
| 141362 |
+
"step": 28370
|
| 141363 |
+
},
|
| 141364 |
+
{
|
| 141365 |
+
"epoch": 228.13,
|
| 141366 |
+
"learning_rate": 9.5578352180937e-06,
|
| 141367 |
+
"loss": 0.482,
|
| 141368 |
+
"step": 28380
|
| 141369 |
+
},
|
| 141370 |
+
{
|
| 141371 |
+
"epoch": 228.21,
|
| 141372 |
+
"learning_rate": 9.55767366720517e-06,
|
| 141373 |
+
"loss": 0.9635,
|
| 141374 |
+
"step": 28390
|
| 141375 |
+
},
|
| 141376 |
+
{
|
| 141377 |
+
"epoch": 228.29,
|
| 141378 |
+
"learning_rate": 9.55751211631664e-06,
|
| 141379 |
+
"loss": 0.3828,
|
| 141380 |
+
"step": 28400
|
| 141381 |
+
},
|
| 141382 |
+
{
|
| 141383 |
+
"epoch": 228.37,
|
| 141384 |
+
"learning_rate": 9.55735056542811e-06,
|
| 141385 |
+
"loss": 0.5989,
|
| 141386 |
+
"step": 28410
|
| 141387 |
+
},
|
| 141388 |
+
{
|
| 141389 |
+
"epoch": 228.45,
|
| 141390 |
+
"learning_rate": 9.55718901453958e-06,
|
| 141391 |
+
"loss": 0.8188,
|
| 141392 |
+
"step": 28420
|
| 141393 |
+
},
|
| 141394 |
+
{
|
| 141395 |
+
"epoch": 228.53,
|
| 141396 |
+
"learning_rate": 9.55702746365105e-06,
|
| 141397 |
+
"loss": 0.4542,
|
| 141398 |
+
"step": 28430
|
| 141399 |
+
},
|
| 141400 |
+
{
|
| 141401 |
+
"epoch": 228.61,
|
| 141402 |
+
"learning_rate": 9.55686591276252e-06,
|
| 141403 |
+
"loss": 1.0006,
|
| 141404 |
+
"step": 28440
|
| 141405 |
+
},
|
| 141406 |
+
{
|
| 141407 |
+
"epoch": 228.69,
|
| 141408 |
+
"learning_rate": 9.55670436187399e-06,
|
| 141409 |
+
"loss": 0.4311,
|
| 141410 |
+
"step": 28450
|
| 141411 |
+
},
|
| 141412 |
+
{
|
| 141413 |
+
"epoch": 228.77,
|
| 141414 |
+
"learning_rate": 9.55654281098546e-06,
|
| 141415 |
+
"loss": 0.5492,
|
| 141416 |
+
"step": 28460
|
| 141417 |
+
},
|
| 141418 |
+
{
|
| 141419 |
+
"epoch": 228.85,
|
| 141420 |
+
"learning_rate": 9.55638126009693e-06,
|
| 141421 |
+
"loss": 1.038,
|
| 141422 |
+
"step": 28470
|
| 141423 |
+
},
|
| 141424 |
+
{
|
| 141425 |
+
"epoch": 228.93,
|
| 141426 |
+
"learning_rate": 9.556219709208402e-06,
|
| 141427 |
+
"loss": 0.4208,
|
| 141428 |
+
"step": 28480
|
| 141429 |
+
},
|
| 141430 |
+
{
|
| 141431 |
+
"epoch": 229.0,
|
| 141432 |
+
"eval_loss": 0.5240156054496765,
|
| 141433 |
+
"eval_runtime": 40.6875,
|
| 141434 |
+
"eval_samples_per_second": 20.645,
|
| 141435 |
+
"eval_steps_per_second": 0.664,
|
| 141436 |
+
"eval_wer": 0.22200059101654845,
|
| 141437 |
+
"step": 28488
|
| 141438 |
+
},
|
| 141439 |
+
{
|
| 141440 |
+
"epoch": 227.02,
|
| 141441 |
+
"learning_rate": 9.556058158319872e-06,
|
| 141442 |
+
"loss": 0.6014,
|
| 141443 |
+
"step": 28490
|
| 141444 |
+
},
|
| 141445 |
+
{
|
| 141446 |
+
"epoch": 227.1,
|
| 141447 |
+
"learning_rate": 9.555896607431342e-06,
|
| 141448 |
+
"loss": 0.4069,
|
| 141449 |
+
"step": 28500
|
| 141450 |
+
},
|
| 141451 |
+
{
|
| 141452 |
+
"epoch": 227.18,
|
| 141453 |
+
"learning_rate": 9.555735056542812e-06,
|
| 141454 |
+
"loss": 0.572,
|
| 141455 |
+
"step": 28510
|
| 141456 |
+
},
|
| 141457 |
+
{
|
| 141458 |
+
"epoch": 227.26,
|
| 141459 |
+
"learning_rate": 9.555573505654282e-06,
|
| 141460 |
+
"loss": 0.7998,
|
| 141461 |
+
"step": 28520
|
| 141462 |
+
},
|
| 141463 |
+
{
|
| 141464 |
+
"epoch": 227.34,
|
| 141465 |
+
"learning_rate": 9.555411954765752e-06,
|
| 141466 |
+
"loss": 0.4765,
|
| 141467 |
+
"step": 28530
|
| 141468 |
+
},
|
| 141469 |
+
{
|
| 141470 |
+
"epoch": 227.42,
|
| 141471 |
+
"learning_rate": 9.555250403877222e-06,
|
| 141472 |
+
"loss": 1.0411,
|
| 141473 |
+
"step": 28540
|
| 141474 |
+
},
|
| 141475 |
+
{
|
| 141476 |
+
"epoch": 227.5,
|
| 141477 |
+
"learning_rate": 9.555088852988692e-06,
|
| 141478 |
+
"loss": 0.4027,
|
| 141479 |
+
"step": 28550
|
| 141480 |
+
},
|
| 141481 |
+
{
|
| 141482 |
+
"epoch": 227.58,
|
| 141483 |
+
"learning_rate": 9.554927302100162e-06,
|
| 141484 |
+
"loss": 0.6805,
|
| 141485 |
+
"step": 28560
|
| 141486 |
+
},
|
| 141487 |
+
{
|
| 141488 |
+
"epoch": 227.66,
|
| 141489 |
+
"learning_rate": 9.554765751211632e-06,
|
| 141490 |
+
"loss": 0.7408,
|
| 141491 |
+
"step": 28570
|
| 141492 |
+
},
|
| 141493 |
+
{
|
| 141494 |
+
"epoch": 227.74,
|
| 141495 |
+
"learning_rate": 9.554604200323102e-06,
|
| 141496 |
+
"loss": 0.4912,
|
| 141497 |
+
"step": 28580
|
| 141498 |
+
},
|
| 141499 |
+
{
|
| 141500 |
+
"epoch": 227.82,
|
| 141501 |
+
"learning_rate": 9.554442649434573e-06,
|
| 141502 |
+
"loss": 0.9956,
|
| 141503 |
+
"step": 28590
|
| 141504 |
+
},
|
| 141505 |
+
{
|
| 141506 |
+
"epoch": 227.9,
|
| 141507 |
+
"learning_rate": 9.554281098546043e-06,
|
| 141508 |
+
"loss": 0.4063,
|
| 141509 |
+
"step": 28600
|
| 141510 |
+
},
|
| 141511 |
+
{
|
| 141512 |
+
"epoch": 227.98,
|
| 141513 |
+
"learning_rate": 9.554119547657513e-06,
|
| 141514 |
+
"loss": 0.6826,
|
| 141515 |
+
"step": 28610
|
| 141516 |
+
},
|
| 141517 |
+
{
|
| 141518 |
+
"epoch": 228.0,
|
| 141519 |
+
"eval_loss": 0.47456440329551697,
|
| 141520 |
+
"eval_runtime": 41.0706,
|
| 141521 |
+
"eval_samples_per_second": 20.453,
|
| 141522 |
+
"eval_steps_per_second": 0.657,
|
| 141523 |
+
"eval_wer": 0.22245412018711766,
|
| 141524 |
+
"step": 28613
|
| 141525 |
+
},
|
| 141526 |
+
{
|
| 141527 |
+
"epoch": 230.06,
|
| 141528 |
+
"learning_rate": 9.553957996768983e-06,
|
| 141529 |
+
"loss": 0.44,
|
| 141530 |
+
"step": 28620
|
| 141531 |
+
},
|
| 141532 |
+
{
|
| 141533 |
+
"epoch": 230.14,
|
| 141534 |
+
"learning_rate": 9.553796445880453e-06,
|
| 141535 |
+
"loss": 0.441,
|
| 141536 |
+
"step": 28630
|
| 141537 |
+
},
|
| 141538 |
+
{
|
| 141539 |
+
"epoch": 230.22,
|
| 141540 |
+
"learning_rate": 9.553634894991923e-06,
|
| 141541 |
+
"loss": 1.109,
|
| 141542 |
+
"step": 28640
|
| 141543 |
+
},
|
| 141544 |
+
{
|
| 141545 |
+
"epoch": 230.3,
|
| 141546 |
+
"learning_rate": 9.553473344103393e-06,
|
| 141547 |
+
"loss": 0.3938,
|
| 141548 |
+
"step": 28650
|
| 141549 |
+
},
|
| 141550 |
+
{
|
| 141551 |
+
"epoch": 230.38,
|
| 141552 |
+
"learning_rate": 9.553311793214863e-06,
|
| 141553 |
+
"loss": 0.5756,
|
| 141554 |
+
"step": 28660
|
| 141555 |
+
},
|
| 141556 |
+
{
|
| 141557 |
+
"epoch": 230.46,
|
| 141558 |
+
"learning_rate": 9.553150242326333e-06,
|
| 141559 |
+
"loss": 0.89,
|
| 141560 |
+
"step": 28670
|
| 141561 |
+
},
|
| 141562 |
+
{
|
| 141563 |
+
"epoch": 230.54,
|
| 141564 |
+
"learning_rate": 9.552988691437803e-06,
|
| 141565 |
+
"loss": 0.459,
|
| 141566 |
+
"step": 28680
|
| 141567 |
+
},
|
| 141568 |
+
{
|
| 141569 |
+
"epoch": 230.62,
|
| 141570 |
+
"learning_rate": 9.552827140549273e-06,
|
| 141571 |
+
"loss": 0.93,
|
| 141572 |
+
"step": 28690
|
| 141573 |
+
},
|
| 141574 |
+
{
|
| 141575 |
+
"epoch": 230.7,
|
| 141576 |
+
"learning_rate": 9.552665589660743e-06,
|
| 141577 |
+
"loss": 0.3949,
|
| 141578 |
+
"step": 28700
|
| 141579 |
+
},
|
| 141580 |
+
{
|
| 141581 |
+
"epoch": 230.78,
|
| 141582 |
+
"learning_rate": 9.552504038772215e-06,
|
| 141583 |
+
"loss": 0.5594,
|
| 141584 |
+
"step": 28710
|
| 141585 |
+
},
|
| 141586 |
+
{
|
| 141587 |
+
"epoch": 230.86,
|
| 141588 |
+
"learning_rate": 9.552342487883685e-06,
|
| 141589 |
+
"loss": 0.8875,
|
| 141590 |
+
"step": 28720
|
| 141591 |
+
},
|
| 141592 |
+
{
|
| 141593 |
+
"epoch": 230.94,
|
| 141594 |
+
"learning_rate": 9.552180936995155e-06,
|
| 141595 |
+
"loss": 0.424,
|
| 141596 |
+
"step": 28730
|
| 141597 |
+
},
|
| 141598 |
+
{
|
| 141599 |
+
"epoch": 231.0,
|
| 141600 |
+
"eval_loss": 0.48454219102859497,
|
| 141601 |
+
"eval_runtime": 41.6364,
|
| 141602 |
+
"eval_samples_per_second": 20.175,
|
| 141603 |
+
"eval_steps_per_second": 0.648,
|
| 141604 |
+
"eval_wer": 0.22036149022500923,
|
| 141605 |
+
"step": 28737
|
| 141606 |
+
},
|
| 141607 |
+
{
|
| 141608 |
+
"epoch": 229.02,
|
| 141609 |
+
"learning_rate": 9.552019386106625e-06,
|
| 141610 |
+
"loss": 0.4394,
|
| 141611 |
+
"step": 28740
|
| 141612 |
+
},
|
| 141613 |
+
{
|
| 141614 |
+
"epoch": 229.1,
|
| 141615 |
+
"learning_rate": 9.551857835218094e-06,
|
| 141616 |
+
"loss": 0.4334,
|
| 141617 |
+
"step": 28750
|
| 141618 |
+
},
|
| 141619 |
+
{
|
| 141620 |
+
"epoch": 229.18,
|
| 141621 |
+
"learning_rate": 9.551696284329564e-06,
|
| 141622 |
+
"loss": 0.762,
|
| 141623 |
+
"step": 28760
|
| 141624 |
+
},
|
| 141625 |
+
{
|
| 141626 |
+
"epoch": 229.26,
|
| 141627 |
+
"learning_rate": 9.551534733441034e-06,
|
| 141628 |
+
"loss": 0.7308,
|
| 141629 |
+
"step": 28770
|
| 141630 |
+
},
|
| 141631 |
+
{
|
| 141632 |
+
"epoch": 229.34,
|
| 141633 |
+
"learning_rate": 9.551373182552504e-06,
|
| 141634 |
+
"loss": 0.4469,
|
| 141635 |
+
"step": 28780
|
| 141636 |
+
},
|
| 141637 |
+
{
|
| 141638 |
+
"epoch": 229.42,
|
| 141639 |
+
"learning_rate": 9.551211631663974e-06,
|
| 141640 |
+
"loss": 1.0086,
|
| 141641 |
+
"step": 28790
|
| 141642 |
+
},
|
| 141643 |
+
{
|
| 141644 |
+
"epoch": 229.5,
|
| 141645 |
+
"learning_rate": 9.551050080775444e-06,
|
| 141646 |
+
"loss": 0.3798,
|
| 141647 |
+
"step": 28800
|
| 141648 |
+
},
|
| 141649 |
+
{
|
| 141650 |
+
"epoch": 229.58,
|
| 141651 |
+
"learning_rate": 9.550888529886914e-06,
|
| 141652 |
+
"loss": 0.7569,
|
| 141653 |
+
"step": 28810
|
| 141654 |
+
},
|
| 141655 |
+
{
|
| 141656 |
+
"epoch": 229.66,
|
| 141657 |
+
"learning_rate": 9.550726978998384e-06,
|
| 141658 |
+
"loss": 0.7594,
|
| 141659 |
+
"step": 28820
|
| 141660 |
+
},
|
| 141661 |
+
{
|
| 141662 |
+
"epoch": 229.74,
|
| 141663 |
+
"learning_rate": 9.550565428109856e-06,
|
| 141664 |
+
"loss": 0.4007,
|
| 141665 |
+
"step": 28830
|
| 141666 |
+
},
|
| 141667 |
+
{
|
| 141668 |
+
"epoch": 229.82,
|
| 141669 |
+
"learning_rate": 9.550403877221326e-06,
|
| 141670 |
+
"loss": 1.0575,
|
| 141671 |
+
"step": 28840
|
| 141672 |
+
},
|
| 141673 |
+
{
|
| 141674 |
+
"epoch": 229.9,
|
| 141675 |
+
"learning_rate": 9.550242326332796e-06,
|
| 141676 |
+
"loss": 0.4467,
|
| 141677 |
+
"step": 28850
|
| 141678 |
+
},
|
| 141679 |
+
{
|
| 141680 |
+
"epoch": 229.98,
|
| 141681 |
+
"learning_rate": 9.550080775444266e-06,
|
| 141682 |
+
"loss": 0.7934,
|
| 141683 |
+
"step": 28860
|
| 141684 |
+
},
|
| 141685 |
+
{
|
| 141686 |
+
"epoch": 230.0,
|
| 141687 |
+
"eval_loss": 0.5488550662994385,
|
| 141688 |
+
"eval_runtime": 40.8782,
|
| 141689 |
+
"eval_samples_per_second": 20.549,
|
| 141690 |
+
"eval_steps_per_second": 0.66,
|
| 141691 |
+
"eval_wer": 0.23211915646659784,
|
| 141692 |
+
"step": 28862
|
| 141693 |
}
|
| 141694 |
],
|
| 141695 |
+
"max_steps": 625000,
|
| 141696 |
"num_train_epochs": 5000,
|
| 141697 |
+
"total_flos": 8.121320456668072e+19,
|
| 141698 |
"trial_name": null,
|
| 141699 |
"trial_params": null
|
| 141700 |
}
|
model-bin/finetune/base/{checkpoint-28240 → checkpoint-28862}/training_args.bin
RENAMED
|
File without changes
|
model-bin/finetune/base/log/1629621463.5203574/events.out.tfevents.1629621463.91f414e9573a.903.91
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d45f1f9f91eb60d9b00f3063ff40b753338f971e552b297ba5cf3f15c2dd97f
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629622131.5072112/events.out.tfevents.1629622131.91f414e9573a.903.93
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81b4069df01358dca8542aa9684f9a1557bab95f5afa45ef951caa6bf7a86e27
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629622785.7860968/events.out.tfevents.1629622785.91f414e9573a.903.95
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6bc9346b8585020baa1737dd9cbcc242329cfcd470b4e2363904efd41d113bfd
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629623445.3943064/events.out.tfevents.1629623445.91f414e9573a.903.97
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef7ca068a2384783e31f6dc4af65bc6a89f7d84e8ed42b319ed1b0a4c5e4a553
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/1629624114.9649696/events.out.tfevents.1629624114.91f414e9573a.903.99
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:906ce6ae2579fa8be4abb9fbadd0894d6387783ebce5ce54ff9d0edd4e8bcfac
|
| 3 |
+
size 4194
|
model-bin/finetune/base/log/events.out.tfevents.1629621463.91f414e9573a.903.90
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:957e5eddd62a4c8d66520a13589fbe2f1bddbaccb52fae86cfc49b8dc1371006
|
| 3 |
+
size 6543
|
model-bin/finetune/base/log/events.out.tfevents.1629622131.91f414e9573a.903.92
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0aa292f1bb65fddc5b2e07b8545728f2b17ee96ef0080df958800299b6e60594
|
| 3 |
+
size 6543
|
model-bin/finetune/base/log/events.out.tfevents.1629622785.91f414e9573a.903.94
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:021f02b40252f149b80504efb3c8534b92a544bea61f83bf908884ac0c5f87e1
|
| 3 |
+
size 6703
|
model-bin/finetune/base/log/events.out.tfevents.1629623445.91f414e9573a.903.96
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad4daea9cb10147666851aec9d5a93eb5b286ae8836f6251db5c365c0c308248
|
| 3 |
+
size 6543
|
model-bin/finetune/base/log/events.out.tfevents.1629624114.91f414e9573a.903.98
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0a28571b4ce9dd9ae1b4daeeec446e7371c691e9d2265858090d70bcbfa6759
|
| 3 |
+
size 6703
|